Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1418 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4937. Min Range: -7.4937
Max Act: 7.4937. Min Act: -0.1700
Data Index: 8663839 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4937. Min Range: -7.4937
Max Act: 7.4000. Min Act: -0.1700
Data Index: 6478975 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4937. Min Range: -7.4937
Max Act: 7.2750. Min Act: -0.1700
Data Index: 5231426 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4937. Min Range: -7.4937
Max Act: 7.2437. Min Act: -0.1700
Data Index: 285410 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4937. Min Range: -7.4937
Max Act: 7.2125. Min Act: -0.1700
Data Index: 1957036 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4937. Min Range: -7.4937
Max Act: 7.1187. Min Act: -0.1700
Data Index: 4863883 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4937. Min Range: -7.4937
Max Act: 7.0875. Min Act: -0.1700
Data Index: 4441301 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4937. Min Range: -7.4937
Max Act: 7.0562. Min Act: -0.1700
Data Index: 5284233 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.9000. Min Act: -0.1700
Data Index: 719913 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.9312. Min Act: -0.1700
Data Index: 1376708 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.9000. Min Act: -0.1700
Data Index: 3141641 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.8687. Min Act: -0.1700
Data Index: 8637458 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.8062. Min Act: -0.1700
Data Index: 3018039 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.8375. Min Act: -0.1700
Data Index: 7849733 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.8062. Min Act: -0.1700
Data Index: 4981803 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.8062. Min Act: -0.1700
Data Index: 1692980 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.8062. Min Act: -0.1700
Data Index: 6093494 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.8062. Min Act: -0.1700
Data Index: 692390 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.8062. Min Act: -0.1700
Data Index: 3336621 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4937. Min Range: -7.4937
Max Act: 6.7750. Min Act: -0.1700
Data Index: 4385360 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19